Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4798 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.6094. Min Act: 0.0000

Data Index: 182018 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.5398. Min Act: -0.0000

Data Index: 869468 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.3069. Min Act: -0.0000

Data Index: 122021 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.2950. Min Act: 0.0000

Data Index: 542126 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.1550. Min Act: -0.0000

Data Index: 203439 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.2495. Min Act: -0.0000

Data Index: 201124 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.2011. Min Act: -0.0000

Data Index: 637518 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.1576. Min Act: -0.0000

Data Index: 758554 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.2566. Min Act: 0.0000

Data Index: 481046 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.6094. Min Range: -2.6094

Max Act: 1.8851. Min Act: -0.0000

Data Index: 1175131 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.0947. Min Act: 0.0000

Data Index: 663356 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.6094. Min Range: -2.6094

Max Act: 1.9676. Min Act: -0.0000

Data Index: 215496 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.0410. Min Act: -0.0000

Data Index: 844928 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.0766. Min Act: -0.0000

Data Index: 1077206 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.0234. Min Act: -0.0000

Data Index: 476918 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1151357 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.0132. Min Act: -0.0000

Data Index: 101305 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 2.6094. Min Range: -2.6094

Max Act: 2.0037. Min Act: 0.0000

Data Index: 1246862 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.6094. Min Range: -2.6094

Max Act: 1.8718. Min Act: 0.0000

Data Index: 15577 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 2.6094. Min Range: -2.6094

Max Act: 1.9667. Min Act: -0.0000

Data Index: 1243432 (C4 (Web Text))

Max Activating Token Index: 978